Conference Paper

Photo and Video Quality Evaluation: Focusing on the Subject

DOI: 10.1007/978-3-540-88690-7_29 Conference: Computer Vision - ECCV 2008, 10th European Conference on Computer Vision, Marseille, France, October 12-18, 2008, Proceedings, Part III
Source: DBLP


Traditionally, distinguishing between high quality professional pho- tos and low quality amateurish photos is a human task. To automatically assess the quality of a photo that is consistent with humans perception is a challenging topic in computer vision. Various differences exist between photos taken by pro- fessionals and amateurs because of the use of photography techniques. Previous methods mainly use features extracted from the entire image. In this paper, based on professional photography techniques, we first extract the subject region from a photo, and then formulate a number of high-level semantic features based on this subject and background division. We test our features on a large and diverse photo database, and compare our method with the state of the art. Our method performs significantly better with a classification rate of 93% versus 72% by the best existing method. In addition, we conduct the first study on high-level video quality assessment. Our system achieves a precision of over 95% in a reason- able recall rate for both photo and video assessments. We also show excellent application results in web image search re-ranking.

Download full-text


Available from: Xiaoou Tang, Feb 22, 2015
    • "Video quality and enjoyment evaluation has been widely investigated in the last few years, and numerous related video databases have been constructed. For example, the: VQEG HDTV database [13]; LIVE video database [36]; IVC video databases [23]; ReTRiEVED video database [31]; video enjoyment database [24], and aesthetic evaluation video database [29]. In these video quality assessment databases, the visual quality of videos derived from different distortion types (e.g., H.264 compression, packet loss and frame rate change) is evaluated by human beings. "
    [Show abstract] [Hide abstract]
    ABSTRACT: Perception of multimedia quality is shaped by a rich interplay between system, context, and human factors. While system and context factors are widely researched, few studies in this area consider human factors as sources of systematic variance. This paper presents an analysis on the influence of personality (Five-Factor Model) and cultural traits (Hofstede Model) on the perception of multimedia quality. A set of 144 video sequences (from 12 short movie excerpts) were rated by 114 participants from a cross-cultural population, producing 1232 ratings. On this data, three models are compared: a baseline model that only considers system factors; an extended model that includes personality and culture as human factors; and an optimistic model in which each participant is modeled as a random effect. An analysis shows that personality and cultural traits represent 9.3% of the variance attributable to human factors while human factors overall predict an equal or higher proportion of variance compared to system factors. In addition, the quality-enjoyment correlation varied across the movie excerpts. This suggests that human factors play an important role in perceptual multimedia quality, but further research to explore moderation effects and a broader range of human factors is warranted.
    No preview · Conference Paper · Oct 2015
  • Source
    • "In [19] [20], Luo and Tang used Matsuda's harmonic templates, along with scene composition features, to assess the aesthetic quality of images. In order to evaluate the quality of photos and videos, Luo and Tang also proposed a method focusing on the subject of images, where the values of the color combination between hue, saturation and brightness were taken into account [21]. Similarly, Charmaret and Urban used the normalized hue distributions of images to calculate each Matsuda's harmonious hue template's weight and applied them to obtain the arc-length distance between each color pair on the hue wheel [22]. "
    [Show abstract] [Hide abstract]
    ABSTRACT: Color harmony is one of the most important features that determine the aesthetics quality of images. The existing color harmony models can be roughly divided into two groups: empirical based models defined by artists and designers and learning based models established by discovering underlying patterns from the collected samples. However, these two types of methods treat the model of color harmony from two distinct aspects and no consolidated framework exists to ensure the benefits can be easily reaped from each other. To overcome this problem, we proposed a Bayesian framework for constructing the color harmony model, in which the empirical rules defined by the artists or designers serve as a prior and the patterns discovered by machine learning methods from the training images are modeled as the likelihood. Particularly, under this framework, we integrate two empirical (Matsuda and Moon-Spencer) color harmony models into a latent Dirichlet allocation (LDA) based learning procedure to train the color harmony model. The experimental results on a public dataset show that the proposed Bayesian based color harmony model is superior to the conventional color harmony models in respect of the image aesthetics assessment.
    Full-text · Article · Apr 2015 · Signal Processing Image Communication
  • Source
    • "Most of recent works perform region of interest (ROI) extraction to enhance their prediction results since different objects locations, shapes or color compositions may change the global aesthetic quality of an image (Datta et al., 2006). ROI may be detected using sharpness estimation (Luo and Tang, 2008), saliency maps (Wong and Low, 2009; Tong et al., 2010) or object detection (Viola and Jones, 2001). "
    [Show abstract] [Hide abstract]
    ABSTRACT: An automated system that provides feedback about aesthetic quality of facial pictures could be of great interest for editing or selecting photos. Although image aesthetic quality assessment is a challenging task that requires understanding of subjective notions, the proposed work shows that facial image quality can be estimated by using low-level features only. This paper provides a method that can predict aesthetic quality scores of facial images. 15 features that depict technical aspects of images such as contrast, sharpness or colorfulness are computed on different image regions (face, eyes, mouth) and a machine learning algorithm is used to perform classification and scoring. Relevant features and facial image areas are selected by a feature ranking technique, increasing both classification and regression performance. Results are compared with recent works, and it is shown that by using the proposed low-level feature set, the best state of the art results are obtained. Copyright © 2015 SCITEPRESS - Science and Technology Publications All rights reserved.
    Full-text · Article · Mar 2015
Show more